Gemini 2.0 Pro Experimental

Nano Banana

Google's Nano Banana image generation and editing model, optimized for fast, high-quality results.

Nano Banana Pro

Higher-quality Nano Banana variant with resolution options up to 4K for premium generations.

Imagen 3

Google's high-quality text-to-image model focused on lighting, detail, and strong visual composition.

Imagen 3 Fast

A faster and cheaper Imagen 3 variant for when speed and cost matter more than maximum quality.

Imagen 4 Ultra

Imagen 4 Ultra prioritizes maximum quality over speed and cost for best-in-class generations.

Imagen 4 Fast

Imagen 4 Fast trades a bit of quality for significantly improved speed and cost.

Gemini 2.5 Flash Image

Gemini 2.5 Flash variant tuned for fast text-to-image generation and simple image edits.

Gemini 1.5 Pro

Gemini 1.5 Pro handles infinite context with 99% retrieval accuracy at 750k tokens via Mixture-of-Experts and generates chapter summaries for 2-hour videos with 92% accuracy.

Gemini 2.5 Pro Experimental

Gemini 2.5 Pro Experimental is Google's advanced model with improved multimodal reasoning, long context understanding with 1 million tokens, and specialized video comprehension.

Gemini 2.0 Flash Thinking

Gemini 2.0 Flash Thinking offers subsecond reasoning with 840 ms median response time for financial forecasting and an energy-efficient architecture using 0.8 kWh per million tokens (40% less than Gemini 1.5).

Gemini 2.5 Flash Preview

Google's state-of-the-art workhorse model, designed for advanced reasoning, coding, mathematics, and scientific tasks. Features hybrid reasoning (thinking on/off) with configurable budgets, balancing quality, cost, and latency.

Gemini 2.5 Flash Preview (thinking)

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.

PaLM 2 Chat

PaLM 2 by Google features improved multilingual, reasoning, and coding capabilities. Optimized for chat-based interactions.

Gemini Pro 1.0

Google's flagship multimodal model (as of release). Designed for natural language tasks, multi-turn chat, code generation, and understanding image inputs.

Gemini 2.5 Pro (I/O Edition)

Our most advanced reasoning model, capable of solving complex problems. Best for multimodal understanding, reasoning over complex problems, complex prompts, tackling multi-step code, math and STEM problems, coding (especially web development), and analyzing large datasets/codebases/documents with long context. Knowledge cutoff Jan 2025.

Gemini 2.5 Flash Preview 05-20

Gemini 2.5 Flash May 20th Checkpoint is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. Note: This model is available in two variants: thinking and non-thinking. The output pricing varies significantly depending on whether the thinking capability is active. If you select the standard variant (without the ":thinking" suffix), the model will explicitly avoid generating thinking tokens. To utilize the thinking capability and receive thinking tokens, you must choose the ":thinking" variant, which will then incur the higher thinking-output pricing. Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter.

Gemini 2.5 Flash Preview 05-20 (thinking)

Gemini 2.5 Flash May 20th Checkpoint is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. Note: This model is available in two variants: thinking and non-thinking. The output pricing varies significantly depending on whether the thinking capability is active. If you select the standard variant (without the ":thinking" suffix), the model will explicitly avoid generating thinking tokens. To utilize the thinking capability and receive thinking tokens, you must choose the ":thinking" variant, which will then incur the higher thinking-output pricing. Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter.

Gemma 3n 4B

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks such as text generation, speech recognition, translation, and image analysis. Leveraging innovations like Per-Layer Embedding (PLE) caching and the MatFormer architecture, Gemma 3n dynamically manages memory usage and computational load by selectively activating model parameters, significantly reducing runtime resource requirements. This model supports a wide linguistic range (trained in over 140 languages) and features a flexible 32K token context window. Gemma 3n can selectively load parameters, optimizing memory and computational efficiency based on the task or device capabilities, making it well-suited for privacy-focused, offline-capable applications and on-device AI solutions.

Gemini 2.5 Pro Preview 06-05

Gemini 2.5 Pro is Google's state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs "thinking" capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities. Pricing: $1.25/M input tokens, $10/M output tokens, $5.16/K input images.

Gemini 2.5 Flash Lite Preview 06-17

Gemini 2.5 Flash Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.

Google: Gemma 3n 2B

Gemma 3n E2B IT is a multimodal, instruction-tuned model developed by Google DeepMind, designed to operate efficiently at an effective parameter size of 2B while leveraging a 6B architecture. Based on the MatFormer architecture, it supports nested submodels and modular composition via the Mix-and-Match framework. Gemma 3n models are optimized for low-resource deployment, offering 32K context length and strong multilingual and reasoning performance across common benchmarks.

Gemma 3 12B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 96000 tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family after Gemma 3 27B.

Gemma 3 27B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 131072 tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2.

Google: Gemini 2.5 Flash Preview 09-2025

Gemini 2.5 Flash Preview September 2025 Checkpoint is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter described in the documentation.

Google: Gemini 2.5 Flash Lite Preview 09-2025

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.

Gemini 3 Flash Preview

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability. The model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.

Gemini 3 Pro Preview

Gemini 3 Pro Preview with high reasoning effort enabled. Exposes full chain-of-thought process for enhanced transparency in complex problem-solving across text, code, and multimodal tasks.